Is Fantoma MCP server safe?
Yes, with the usual care.
Safe to use. Minor gaps such as a missing repository or slower maintenance.
What to know before installing
- highShell command built from a string (injection risk)
How Fantoma compares
Against every graded Scraping and browsing MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 74/100
- higher than 40% of 868 Scraping and browsing servers
- Tools that change things
- 20%
- typical: 0%. Fewer write tools means less an agent can break
What its tools let an agent do: 4 read · 1 change
Public scan report
scanner v0.1.10 · 2026-10-13 · same rubric, same numbers if you re-run it
1 high
- Code scan73 source files scanned13/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Findings (1)
- highShell command built from a string (injection risk)
exec.shell-concatfantoma-0.11.3/fantoma/cli.py: … monitor_path.exists(): os.system(f"{sys.executable} {monitor_path} --quick"…
Overall 74/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON
Other servers that do what Fantoma does
- FortressStealth browser for AI agents: fetch pages behind Cloudflare/DataDome/CAPTCHA, extract clean data.not reviewedEstablishedB
- AIHawkAI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.not reviewedWidely usedA
- UnbrowseWebsites as APIs: read pages, run site tasks via learned APIs, cloud browser with saved logins.not reviewedEstablishedA